DeepEval

Framework / harness (not an eval — tooling/reference entry)

Pytest-style LLM eval framework incl. hallucination and safety metrics.

Category

Eval frameworks & harnesses

Insurance exposure

Hallucination

Publisher

Confident AI

Publisher type

Company (open source)

License

Apache-2.0

Status

Active (<90d)

Last commit

2026-10-15

Stars

18892

View source on GitHub →

Wanich Risk Lab, 2026.